Messages in this thread | | | Date | Wed, 18 Jan 2012 16:32:36 +0300 | From | Sergey Senozhatsky <> | Subject | Re: x86/mce: machine check warning during poweroff |
| |
On (01/18/12 18:45), Srivatsa S. Bhat wrote: > Date: Wed, 18 Jan 2012 18:45:55 +0530 > From: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com> > > > On Tue, 2012-01-17 at 15:22 +0530, Srivatsa S. Bhat wrote: > >> Thanks for the patch, but unfortunately it doesn't fix the problem! > >> Exactly the same stack traces are seen during a CPU Hotplug stress test. > >> (I didn't even have to stress it - it is so fragile that just a script > >> to offline all cpus except the boot cpu was good enough to reproduce the > >> problem easily.) > > > > hmm, that's weird. with the patch, sched_ilb_notifier() should have > > cleared the cpu going offline from the nohz.idle_cpus_mask. And this > > should have happened after that cpu is removed from active mask. So > > no-one else should add that cpu back to the nohz.idle_cpus_mask and this > > should prevent the issue from happening. > > Just a small note, since you're talking about removing CPU from nohz.idle_cpus_mask, that I'm able to reproduce this problem not only when offlining CPU, but during onlininig as well (kernel 3.3):
[ 67.587942] CPU1 is up [ 67.589710] Call Trace: [ 67.589719] <IRQ> [<ffffffff81030092>] warn_slowpath_common+0x7e/0x96 [ 67.589745] [<ffffffff810300bf>] warn_slowpath_null+0x15/0x17 [ 67.589762] [<ffffffff81018ff7>] native_smp_send_reschedule+0x25/0x56 [ 67.589783] [<ffffffff81067ffe>] trigger_load_balance+0x6ac/0x72e [ 67.589802] [<ffffffff81067bfd>] ? trigger_load_balance+0x2ab/0x72e [ 67.589823] [<ffffffff8105f05c>] scheduler_tick+0xe2/0xeb [ 67.589842] [<ffffffff8103f6ac>] update_process_times+0x60/0x70 [ 67.589863] [<ffffffff8107c1e1>] tick_sched_timer+0x6d/0x96 [ 67.589882] [<ffffffff81053b3b>] __run_hrtimer+0x1c2/0x3a1 [ 67.589900] [<ffffffff8107c174>] ? tick_nohz_handler+0xdf/0xdf [ 67.589918] [<ffffffff81054721>] hrtimer_interrupt+0xe6/0x1b0 [ 67.589937] [<ffffffff81019bdd>] smp_apic_timer_interrupt+0x80/0x93 [ 67.589958] [<ffffffff814a2f73>] apic_timer_interrupt+0x73/0x80 [ 67.589975] <EOI> [<ffffffff81087bf1>] ? generic_exec_single+0x73/0x8a [ 67.590000] [<ffffffff81087bea>] ? generic_exec_single+0x6c/0x8a [ 67.590019] [<ffffffff81017f8b>] ? get_fixed_ranges.constprop.5+0x10b/0x10b [ 67.590039] [<ffffffff81087d2c>] smp_call_function_single+0x124/0x15c [ 67.590059] [<ffffffff81017f8b>] ? get_fixed_ranges.constprop.5+0x10b/0x10b [ 67.590081] [<ffffffff8101696d>] mtrr_save_state+0x19/0x1b [ 67.590100] [<ffffffff8148bf67>] native_cpu_up+0xa1/0x138 [ 67.590117] [<ffffffff8148d192>] _cpu_up+0x92/0xfc [ 67.590134] [<ffffffff8147f3eb>] enable_nonboot_cpus+0x48/0xad [ 67.590154] [<ffffffff8106f080>] suspend_devices_and_enter+0x21a/0x407 [ 67.590173] [<ffffffff8106f391>] enter_state+0x124/0x169 [ 67.590191] [<ffffffff8106e01b>] state_store+0xb7/0x101 [ 67.590212] [<ffffffff8126c82f>] kobj_attr_store+0x17/0x19 [ 67.590230] [<ffffffff8117e20c>] sysfs_write_file+0x103/0x13f [ 67.590249] [<ffffffff8111f018>] vfs_write+0xad/0x13d [ 67.590266] [<ffffffff8111f293>] sys_write+0x45/0x6c [ 67.590282] [<ffffffff814a2439>] system_call_fastpath+0x16/0x1b
Sergey
> > I could reproduce the problem easily with out the patch but when I > > applied the patch I couldn't recreate the issue. Srivatsa, can you > > please re-check the kernel you tested indeed has the fix? > > > > re-Reviewing the code/patch also doesn't give me a hint. > > > >> I have a few questions regarding the synchronization with CPU Hotplug. > >> What guarantees that the code which selects and IPIs the new ilb is totally > >> race-free with respect to CPU hotplug and we will never IPI an offline CPU? > > > > So, nohz_balancer_kick() gets called only from interrupts disabled. > > During that time (from selecting the ilb_cpu to sending the IPI), no cpu > > can go offline. As the offline happens from the stop-machine process > > context with interrupts disabled. > > > > Only thing we need to make sure is the offlined cpu shouldn't be part of > > the nohz.idle_cpus_mask and for post 3.2 code, posted patch ensures > > that. > > > > For 3.2 and before, when a cpu exits tickless idle, it gets removed from > > the nohz.idle_cpus_mask (and also from the nohz.load_balancer). And if > > the cpu is not in the active mask (while going offline), subsequent > > calls to select_nohz_load_balancer() ensures that the cpu going down > > doesn't update the nohz structures. So I thought 3.2 shouldn't exhibit > > this problem. > > > > > >> (As demonstrated above, this issue is in 3.2-rc7 > >> as well.) > > > > hmm, don't think we ran into this before 3.2. So, what am I missing from > > the above? I will try to reproduce it on 3.2 too. > > > > > I tested again on 3.2. I didn't hit those warnings (IPI to offline cpus). > It happens only in the post-3.2 kernel. > > Regards, > Srivatsa S. Bhat > IBM Linux Technology Center >
| |